Estimation of Alveolar Bone Loss in Periodontitis Using Machine Learning

• Published in: International dental journal Vol. 72; no. 5; pp. 621 - 627
• Main Authors: Tsoromokos, Nektarios, Parinussa, Sarah, Claessen, Frank, Moin, David Anssari, Loos, Bruno G.
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.10.2022; Elsevier
• Subjects: Alveolar bone loss; Convolutional neural network; Machine learning; Periapical radiographs; Periodontitis; Scientific Research Report; Periodontitis; Convolutional neural network; Alveolar bone loss; Periapical radiographs; Machine learning
• ISSN: 0020-6539; 1875-595X
• DOI: 10.1016/j.identj.2022.02.009

The objective of this research was to perform a pilot study to develop an automatic analysis of periapical radiographs from patients with and without periodontitis for the percentage alveolar bone loss (ABL) on the approximal surfaces of teeth using a supervised machine learning model, that is, convolutional neural networks (CNN). A total of 1546 approximal sites from 54 participants on mandibular periapical radiographs were manually annotated (MA) for a training set (n = 1308 sites), a validation set (n = 98 sites), and a test set (n = 140 sites). The training and validation sets were used for the development of a CNN algorithm. The algorithm recognised the cemento-enamel junction, the most apical extent of the alveolar crest, the apex, and the surrounding alveolar bone. For the total of 140 images in the test set, the CNN scored a mean of 23.1 ± 11.8 %ABL, whilst the corresponding value for MA was 27.8 ± 13.8 %ABL. The intraclass correlation (ICC) was 0.601 (P < .001), indicating moderate reliability. Further subanalyses for various tooth types and various bone loss patterns showed that ICCs remained significant, although the algorithm performed with excellent reliability for %ABL on nonmolar teeth (incisors, canines, premolars; ICC = 0.763). A CNN trained algorithm on radiographic images showed a diagnostic performance with moderate to good reliability to detect and quantify %ABL in periapical radiographs.